RepairFormer: Automated Repair of Structured Inputs Using Transformers

arXiv:2608.05060 · cs.SE, cs.AI · Submitted 2026-08-05 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-08-05

Updated: 2026-08-05

Comments: 5 pages, 2 figures, and 3 tables

Journal ref: SPLASH Companion '26: Companion Proceedings of the 2026 ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity

DOI: 10.1145/3837729.3840497

Code: https://github.com/pass-uh/RepairFormer

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties